Nemotron3 Nano 4B Aggressive needs about 10.4 GB of memory at Q4_K_M (a 2.8 GB file) with an 8K context window, so it fits on a 12 GB GPU. This repository has 12 quants, from 2.2 GB (IQ2_M) to 4.7 GB (Q8_K). Longer context needs more: at 32K tokens the KV cache alone adds about 28.2 GB.
Nemotron3 Nano 4B Aggressive is a 3.97B-parameter Nemotron model in GGUF format, quantized by nazihara. Its trained context length is 1024K tokens. The repository has 12 quant files, from 2.2 GB (IQ2_M) to 4.7 GB (Q8_K).
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| IQ2_M | 2.2 GB | 9.7 GB | Too big | Get file → | |
| IQ3_M | 2.3 GB | 9.9 GB | Too big | Get file → | |
| Q2_K | 2.3 GB | 9.9 GB | Too big | Get file → | |
| Q3_K_M | 2.4 GB | 9.9 GB | Too big | Get file → | |
| IQ4_XS | 2.4 GB | 10.0 GB | Too big | Get file → | |
| Q3_K | 2.5 GB | 10.1 GB | Too big | Get file → | |
| Q4_K_M | 2.8 GB | 10.4 GB | Too big | Get file → | |
| Q4_K | 3.0 GB | 10.6 GB | Too big | Get file → | |
| Q5_K_M | 3.1 GB | 10.6 GB | Too big | Get file → | |
| Q5_K | 3.3 GB | 10.8 GB | Too big | Get file → | |
| Q6_K | 4.0 GB | 11.6 GB | Too big | Get file → | |
| Q8_K | 4.7 GB | 12.2 GB | Too big | Get file → |
What GPU do you need for Nemotron3 Nano 4B Aggressive?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: the best quant that fits is Q6_K (4.0 GB file, about 11.6 GB in use).
- 16 GB VRAM: the best quant that fits is Q8_K (4.7 GB file, about 12.2 GB in use).
Which Nemotron3 Nano 4B Aggressive quant should you choose?
Q4_K_M is the usual starting point for Nemotron3 Nano 4B Aggressive: it balances file size and quality well. Here it is a 2.8 GB file.
If memory is tight, the smallest file is IQ2_M at 2.2 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about Nemotron3 Nano 4B Aggressive
How much VRAM does Nemotron3 Nano 4B Aggressive need?
About 10.4 GB at Q4_K_M with an 8K context window. That is the 2.8 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run Nemotron3 Nano 4B Aggressive on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 9.7 GB, so you would need a larger GPU or CPU offloading.
What is the file size of Nemotron3 Nano 4B Aggressive GGUF?
It depends on the quant: IQ2_M is 2.2 GB, IQ3_M is 2.3 GB, Q2_K is 2.3 GB, Q3_K_M is 2.4 GB, IQ4_XS is 2.4 GB, Q3_K is 2.5 GB and 6 more.
What context length does Nemotron3 Nano 4B Aggressive support?
The GGUF header lists a trained context length of 1,048,576 tokens (1024K). The KV cache grows with the context you use: about 7.0 GB at 8K and 28.2 GB at 32K.
Where can I download Nemotron3 Nano 4B Aggressive GGUF?
The files are on Hugging Face in the nazihara/Nemotron3-Nano-4B-Aggressive repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does Nemotron3 Nano 4B Aggressive use?
Hugging Face lists the license as other. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.